AI Agent StoreMicrosoft · Hosted decision model · Preview
Microsoft Decision-1
Classify a ticket, choose a workflow step or grade an answer against your rubric. Microsoft’s new text-only decision model returns probabilities over the options you supply, rather than writing a response.
Released 2026-10-09 · First reviewed 2026-10-10 · Checked 2026-10-15.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact AI Gateway route ID: microsoft/microsoft-decision-1. Foundry lists Microsoft-Decision-1 version 1 as Preview. The confirmed Gateway route supports yes/no, choice and ordered scoring, with multiple questions sharing input. It needs a Gateway key without a separate Azure deployment.
Microsoft names Qwen3.5-9B as the base and publishes its own comparisons. Parent-model scores and vendor speed claims are not independent results for Decision-1. OpenRouter is linked by the announcement but the route is absent from the current general catalog; Foundry and Gateway availability are separately verified.
Foundry and Gateway agree on 32,768 input tokens. A maximum number of questions and a cache-read price remain unverified. It does not generate explanations or accept images.
Output: Probabilities for supplied yes/no, choice and rating options; no generated explanations. Compare decision models, limits and input costs ↗
Microsoft lists $0.042 per million input tokens and free answers; AI Gateway lists the same rate. Check how your service counts background information shared across questions. This is a token-price comparison, not a measured total bill or cost per correct decision. Use actual billed usage and the model named in each response to check your estimate.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Check whether confidence scores match the answers you can verify.
Compare caching and long-context costs ↗